File size: 250 Bytes
5238d08
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
{
  "model_type": "scratch_transformer",
  "architectures": [
    "ScratchTransformer"
  ],
  "vocab_size": 8000,
  "d_model": 256,
  "n_layers": 16,
  "n_heads": 16,
  "d_ff": 512,
  "max_seq_len": 4096,
  "dropout": 0.1,
  "name": "scratch-model"
}